# Scan: ByTheLaw > GAMMA-Ray v0.0.155 (beta, for review; every rating is experimental). An example GAMMA-Ray beta rating of ByTheLaw: freedom 1, 1, 1 across its configurations; deployment governance not assessed. > Page: https://gamma-ray.sgit.ai/scans/bythelaw-legal-chat/ · Source: data/scans/bythelaw-legal-chat.json Example · beta rating · a product as its vendor documents it · read 2026-11-10 · not seen by the vendor Chat assistant that answers legal questions with citations to official Portuguese and EU sources, analyses uploaded documents, drafts contracts, emails and translations, and organises work in projects. The site menu names it 'ByTheLaw: Legal research and knowledge'; the help centre calls it 'Legal Chat'. A scan of a product as its vendor documents it, not of any one deployment. Made by the report studio: a researcher-assessor, a challenger, then the scorer. Part of the first Portuguese cohort. Built only from ByTheLaw's own public pages (product, documentation, blog, customer stories, legal and security pages). Nothing was tested. If you are the vendor and something here is wrong, the correction will be made and dated. *Figure. The label for this rating; its contents are in the text.* 1 Freedom as shipped Answers 1 Freedom at most Answers 7 Controls it brings as shipped n/a Deployment governance not assessed ## How to read it This is a product, not a deployment. A product has no owner, no policy in force and no mandate until somebody runs it, so it is given **no governance level and no level held**: those belong to a deployment. What a product has is a freedom level for each way it can be configured, and a list of the controls each configuration brings. *Figure. The freedom level of each configuration; the table has the same.* | Configuration | What changes | Freedom | Controls | Turned on by the operator | |---|---|---|---|---| | **As shipped** | ByTheLaw (Legal Chat) with its documented defaults. | 1 Answers | 7 | nothing | | **Citius** | Citius integration: experimental, free, granted by ByTheLaw to selected users who enter their own Citius credentials; read-only access to court notifications, hearings and case movements. | 1 Answers | 11 | it connects to external tools or services across a trust boundary; its autonomy limits and the tools it may use are defined; high-impact actions need a person's approval; a limit on it is a rule in prose; incidents and errors are communicated to those affected | | **Project sources** | Per-project source restriction: the user switches individual official sources on or off for a project. | 1 Answers | 8 | a limit on it is a setting that its own account could change | The same product is a different agent in each row. A rating of a deployment starts by saying which row it is. An indicator with no evidence is reported as not evidenced; it is never read as a no. ## The profile *Figure. One square per indicator, by question; every answer is listed below.* ## The grant: what it can actually do The questions measure what is said about an agent: its purpose, its rules, its controls. The grant is the other half: what its permissions let it do, capability by capability, and what stands in the way of each. This is RiskMandate's measurement, and it depends on the permissions a deployment was given. **Not measured.** Not measured. No deployment shape for this product is published in the capability grammar. ## Seen, and not credited - The scheduled Citius reading (I08 executes actions itself; I17 routine tasks, person consulted on exceptions) In the Citius configuration ByTheLaw reads Citius automatically at a periodicity it chooses (terms 2.2 b; llms.txt names 11:00, 14:00 and 17:00 Lisbon time), so these reads are not prompted by the person. The terms limit it to consulting and reading with no procedural acts (2.3), and an unread notification is opened only after the user's express action (2.4): automated retrieval, not an action executed for the user, so I08 and I17 are not credited and I15 is read for the chat only. [Source](https://app.bythelaw.com/pt/termos-citius) - The self-description as fully autonomous (I19) llms.txt calls the product a fully autonomous Legal AI; a self-description with no described independent actions is not evidence of autonomy, and the actions the same file describes for this product are read-only Citius checks. [Source](https://bythelaw.com/llms.txt) - It recommends actions (I07) The help page shows retrieval (answers grounded in official sources, with citations the lawyer verifies before a filing) but no recommendation of actions; half of the indicator is not credited as the whole. [Source](https://help.bythelaw.com/en/o-que-e-a-bythelaw/) ## What its evidence reaches *Figure. The mashup graph with this agent's evidenced indicators lit.* ## Every answer, with its source ### What is the agent built on? - **As shipped.** It is a vendor's assistant, used as supplied. The help centre describes ByTheLaw as its own AI platform built for lawyers and legal teams; that customers use it as supplied is the scan's reading of a vendor platform. [Source](https://help.bythelaw.com/en/o-que-e-a-bythelaw/) (documented) - *Not evidenced.* It runs on an AI platform with the organisation's own data, without executing arbitrary code. - *Not evidenced.* It is configured on a low-code or no-code builder and acts on real organisational data. - *Not evidenced.* It generates and executes code with local or cloud privileges. - *Not evidenced.* It is built in-house: the organisation controls its identity, tools and boundaries. ### Does it act, or only answer and recommend? - *Not evidenced.* It follows fixed rules, with no reasoning. - *Not evidenced.* It retrieves information and recommends actions; a person acts. - *Not evidenced.* It executes actions itself. - *Not evidenced.* It is in production: a public source names a customer or gives usage figures for what it does on its own. ### How far does it reach? - **As shipped.** It works in one domain's data. It works on legal material: Portuguese and European legislation, case law and the user's uploaded documents. [Source](https://bythelaw.com/en/) (documented) - *Not evidenced.* It works across several domains or systems. - **Available, if the operator turns it on.** It connects to external tools or services across a trust boundary. The Citius integration uses the lawyer's own Citius credentials to read the courts system automatically, and Citius can be a source of the chat on request and approval; experimental, granted by ByTheLaw to selected users. [Source](https://app.bythelaw.com/pt/termos-citius) (documented) ### Does it work with other agents? - *Not evidenced.* Several agents coordinate inside the organisation. - *Not evidenced.* Agents operate across organisational boundaries or disparate stacks. - *Not evidenced.* There is a published protocol or communication layer between agents. - *Not evidenced.* Others build on it: third parties publish integrations, skills or agents for it. - *Not evidenced.* It exposes an agent interface: a published MCP server, an agent card, or an API documented for agents to call. ### What is the person's role? - **As shipped.** The person operates: every action is prompted and controlled by them. In the chat as shipped, the lawyer writes each request and the assistant returns an answer to it; this credit is for the chat only, since in the optional Citius configuration ByTheLaw reads Citius on its own schedule without a prompt (see not credited). [Source](https://help.bythelaw.com/en/escrever-o-primeiro-prompt/) (documented) - *Not evidenced.* The agent suggests; the person reviews and approves each action. - *Not evidenced.* The agent handles routine tasks; the person is consulted on exceptions. - *Not evidenced.* The agent works independently; the person approves critical decisions only. - *Not evidenced.* The agent has full autonomy within boundaries; the person monitors. ### Is what it is for written down? - **As shipped.** Its purpose and permitted tasks are stated in writing. The help centre lists what the assistant is for: legal questions, document analysis, drafting, reading legislation, organising work. [Source](https://help.bythelaw.com/en/o-que-e-a-bythelaw/) (documented) - **Available, if the operator turns it on.** Its autonomy limits and the tools it may use are defined. The Citius terms limit the integration to reading and consulting, and state it performs no procedural acts. [Source](https://app.bythelaw.com/pt/termos-citius) (documented) - **As shipped.** Its limits and known failure cases are documented for those who use it. Help pages document limits of use, such as upload limits and that files attached inside an email are not opened. [Source](https://help.bythelaw.com/en/formatos-limites-e-ocr/) (documented) ### Does it have its own identity and only the access it needs? - *Not evidenced.* What it can reach is enumerated: scopes, permissions, tools. - *Not evidenced.* Its authorisation is published as metadata that anyone can read. - *Not evidenced.* It asks for narrower access than the whole account. - *Not evidenced.* It has its own identity, separate from any person's. - *Not evidenced.* Its identity is cryptographic and can be checked by others. - *Not evidenced.* Its tokens are bound to the service they were issued for and are not passed on. ### Is it in a registry, with an owner? - *Not evidenced.* The organisation keeps a registry of its agents. - *Not evidenced.* Each agent has a named owner. - *Not evidenced.* Agents are retired by a defined process. ### Who is accountable for it? - *Not evidenced.* A named executive or body is accountable for the organisation's agents. - *Not evidenced.* Roles and responsibilities for AI risk are documented. ### Is there a policy that governs it? - *Not evidenced.* A governance policy for agents is published. - *Not evidenced.* Agents and use cases are classed by risk. - **As shipped.** The laws that apply to it are identified. The GDPR is named as the law under which personal data in the platform is processed. [Source](https://help.bythelaw.com/en/privacidade-e-dados/) (documented) - *Not evidenced.* New agents pass an approval or review before they run. ### Can a person step in or stop it? - **Available, if the operator turns it on.** High-impact actions need a person's approval. In the Citius integration, an unread notification is opened (which marks it read in Citius, irreversibly) only after the user's prior express action, preceded by a warning. [Source](https://app.bythelaw.com/pt/termos-citius) (documented) - **As shipped.** There is a way to pause or stop it. A release note of 21 December 2025 announces a stop button that interrupts an answer while it is generated, on the Free, Pro and Pro Teams plans. [Source](https://help.bythelaw.com/novidades/soft-law-financeira-e-controlo-das-respostas/) (documented) - *Not evidenced.* There is a defined escalation path. ### Is what it does logged? - *Not evidenced.* Its actions are logged. - *Not evidenced.* The log is tamper-evident and kept for a stated time. ### Is it watched while it runs? - *Not evidenced.* It is monitored in operation. - *Not evidenced.* Anomalies are detected in real time and raise alerts. ### What stands between it and what it should not do? - *Not evidenced.* A limit on it is enforced by something outside its own reach. - **Available, if the operator turns it on.** A limit on it is a setting that its own account could change. A user can restrict, per project, which sources answers draw on; it is a setting the user's own account changes. [Source](https://help.bythelaw.com/en/escolher-as-fontes-de-um-projeto/) (documented) - **Available, if the operator turns it on.** A limit on it is a rule in prose. The Citius terms state in prose that the authorisation covers only consulting and reading. [Source](https://app.bythelaw.com/pt/termos-citius) (documented) - *Not evidenced.* Policy is enforced as machine-readable rules. - *Not evidenced.* The difference between what it can reach and what it is for is stated. ### Is it tested, and are the results shown? - *Not evidenced.* Test or evaluation results are published. - *Not evidenced.* It is tested for safety and security, including by attack. - *Not evidenced.* People who did not build it take part in assessing it. ### What happens when it goes wrong? - *Not evidenced.* There is an incident process for agents. - **Available, if the operator turns it on.** Incidents and errors are communicated to those affected. The Citius terms commit to notifying the user without undue delay of a security breach affecting credentials or data. [Source](https://app.bythelaw.com/pt/termos-citius) (documented) - *Not evidenced.* There is a plan for a failure of a third party it depends on. ### Do people know it is an AI, and can they answer back? - *Not evidenced.* It tells the people it talks to that it is an AI. - **As shipped.** There is a channel to report problems with it or contest its output. A release note of 21 May 2026 announces a report-error button as a popup over the help icon and on messages that failed, on all plans. [Source](https://help.bythelaw.com/novidades/pesquisa-web-para-todos-e-novo-perfil/) (documented) - **As shipped.** It is machine-readable for agents: it publishes an llms.txt, an AGENTS.md, an API description or an agent card. The site publishes an llms.txt describing the product and its pages; fetched and resolving on 10 November 2026. [Source](https://bythelaw.com/llms.txt) (observed) ### What data does it use, and under what rules? - **As shipped.** The data it uses is described. The help centre lists the legislative, case-law and regulatory databases answers are drawn from. [Source](https://help.bythelaw.com/en/fontes-oficiais/) (documented) - *Not evidenced.* There are data quality rules for what it reads. - *Not evidenced.* Its privacy risk has been examined. ### What does it depend on from others? - *Not evidenced.* The models and third-party components it uses are listed. - *Not evidenced.* Third-party components are monitored and have risk controls. ### Has anyone independent checked? - *Not evidenced.* A public certificate or audit report covers it. - *Not evidenced.* Compliance evidence is produced continuously, ready for a regulator. ### Is the organisation behind it ready? - *Not evidenced.* There is a stated strategy for agents. - *Not evidenced.* The people who work with it are trained. - *Not evidenced.* Its value is measured. - *Not evidenced.* It is improved on a regular cycle. - *Not evidenced.* The organisation's risk management covers agents. ## The vault This rating, its evidence list, its grant and the questions it was made against are kept in a public sgit vault (`dllzmbc3`, published 2026-11-10). Anyone can read it with this key: `sgit_public_read_7f528ecd6fbd9c2d0f293f8361fd3ad93d4ea63fd8b1f1a70ec77feb04110bb6:dllzmbc3` With [sgit](https://sgit.ai/): `sgit clone sgit_public_read_7f528ecd6fbd9c2d0f293f8361fd3ad93d4ea63fd8b1f1a70ec77feb04110bb6:dllzmbc3`. The key reads; it cannot write. An operator who wants to add what only they hold forks the vault into a private one.